The Application of Artificial Intelligence in Well Test Analysis
Abstract/Contents
- Abstract
- Much work has been directed toward the automation of well test interpretation. The automation of the model identification is a necessary step in reaching this goal. The objective of this thesis is to present some developments in the use of Artificial Intelligence (AI) in well test analysis. A target of AI application in the field of well test analysis is to identify well test models. This work explores the possibility of using a database expert system to perform this task.A significant advantage of the database approach is the reduced memory required. When symbols are used instead of the normal description, the database system requires only a fraction of memory that is used by rule-based system. The technique offers improved readability over that of rule-based systems. In most cases, less time is required to run a database program than a rule-based program. Currently the database approach gives more solutions than a rule-based system. Unlike a rule-based system which finds a solution by matching the problem both quantitatively and qualitatively, a database system finds a solution only qualitatively. To preserve completeness, all candidates that match the problem qualitatively are listed as solutions.Experiments with generated as well as field data showed that in at least one occasion a rules-based system failed to find the right model. While for the same problem, a database system gave all the "wrong" models that are predicted by a rule-based system, together with the right model.
Description
Type of resource | text |
---|---|
Date created | March 1991 |
Creators/Contributors
Author | Gao, Guozheng |
---|---|
Primary advisor | Horne, Roland N. |
Advisor | Ramey, Jr., Henry J. |
Degree granting institution | Stanford University, Department of Petroleum Engineering |
Subjects
Subject | School of Earth Energy & Environmental Sciences |
---|---|
Genre | Thesis |
Bibliographic information
Access conditions
- Use and reproduction
- User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
Preferred citation
- Preferred Citation
- Gao, Guozheng. (1991). The Application of Artificial Intelligence in Well Test Analysis. Stanford Digital Repository. Available at: https://purl.stanford.edu/bb654mz9296
Collection
Master's Theses, Doerr School of Sustainability
View other items in this collection in SearchWorksContact information
- Contact
- brannerlibrary@stanford.edu
Also listed in
Loading usage metrics...